Sophia Sanborn (@naturecomputes) / X

Sophia Sanborn

785 posts

Sophia Sanborn

@naturecomputes

Scientist / Founder | Neuro + AI | Prof @stanford | enigmaproject.ai & @metamorphiclabs

San Francisco

Joined March 2018

Pinned
Sophia Sanborn
@naturecomputes
Jun 16
🧠 Mechanistic interpretability for the brain 🧠 Early visual neurons have had a clean mathematical description for decades (Gabor functions), while higher visual areas have remained notoriously hard to characterize. Our new paper, led by @vedanglad, shows that natural language
Vedang Lad
@vedanglad
Jun 16
How well can you describe the feature selectivity of a vision neuron … with words? Interpretability has long borrowed from neuroscience — and maybe it can give back too! 🧵
00:00
12K
Sophia Sanborn
@naturecomputes
Apr 21, 2023
This figure summarizes the landscape of topological neural network architectures on hypergraphs, simplicial, cellular, & combinatorial complexes in a unified graphical notation. Check out our paper and full repository of TNN equations for more ✨
Mathilde Papillon🦋 mathildepapillon .bsky .social
@mathildepapillo
Apr 21, 2023
Topological Deep Learning is an immensely powerful and fast emerging field. Our new literature review arxiv.org/abs/2304.10031 is out and here’s why I’m very excited about it🧵1/5
151K
Sophia Sanborn
@naturecomputes
Aug 6, 2024
New project: enigmaproject.ai Engineers, ML researchers, mech interp community: Reach out if you're interested in getting involved
249K
Sophia Sanborn
@naturecomputes
Jul 15, 2024
Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures New review out with @ninamiolane, co-led by myself, @johmathe & @mathildepapillo Check out our visual taxonomies of non-Euclidean structure in data & ML models
64K
Sophia Sanborn
@naturecomputes
May 2, 2023
Bispectral Neural Networks go to #ICLR2023! In this work, we present a new neural network architecture capable of learning unknown groups purely from the symmetries implicit in data —with @cashewmake2, Bruno Olshausen, and Christopher Hillar 1/17
70K
Sophia Sanborn
@naturecomputes
Dec 22, 2023
In this new paper, led by @giovannimarchet, we present a unique theoretical result that provides guarantees for the concrete representational structure expected to emerge in a learning system
Giovanni Luca Marchetti
@giovannimarchet
Dec 22, 2023
Glad to announce our new preprint with C. Hillar, D. Kragic, and @naturecomputes ! arxiv.org/abs/2312.08550 We show via group theory how Fourier features emerge in invariant neural networks -- a step towards a mathematical understanding of representational universality. 🧵1/n
65K
Sophia Sanborn
@naturecomputes
Nov 14, 2023
🎉 If you're interested in working on understanding visual representations in deep networks through the lens of symmetry & geometry, the @geometric_intel lab is recruiting!
Geometric Intelligence Lab
@geometric_intel
Nov 14, 2023
📣 The Geometric Intelligence lab receives a 1.2M$ NSF Grant to work on Lie Group Representation Learning for Vision Lead by lab members Christian Shewmake and Sophia Sanborn, the grant will support research on vision models that incorporate hierarchical learnable symmetries
78K
Sophia Sanborn
@naturecomputes
Jul 7, 2022
Our workshop on Symmetry and Geometry in Neural Representations has been accepted to @NeurIPSConf 2022! We've put together a lineup of incredible speakers and panelists from 🧠 neuroscience, 🤖 geometric deep learning, and 🌐 geometric statistics.
Sophia Sanborn
@naturecomputes
Jul 22, 2024
My talk from the Mathematics of Neuroscience & AI conference in Rome is now online - featuring work with @giovannimarchet on Symmetry & Universality Thanks to the organizers, esp @RMBattleday, for putting on such a fantastic event
16K
Sophia Sanborn
@naturecomputes
Jul 5, 2023
If you find this interesting, check out our ICLR 2023 paper, in which we demonstrate that you can *learn* group-Fourier transforms by learning to be invariant to transformations in data: arxiv.org/pdf/2209.03416…
Gabriel Peyré
@gabrielpeyre
Jul 5, 2023
Representation theory defines a Fourier transform on groups. Finite commutative groups correspond to the classical discrete Fourier transform. en.wikipedia.org/wiki/Represent… en.wikipedia.org/wiki/Fourier_t…
40K
Sophia Sanborn
@naturecomputes
Apr 22, 2024
Seeking: Creative and ambitious computational neuroscience / ML PhDs interested in building next-generation brain-computer interfaces. My team at science.xyz is hiring research scientists. Reach out at [email protected] for more info.
Science | Science Corporation
From science.xyz
59K
Sophia Sanborn
@naturecomputes
Jan 21, 2024
About a month ago, I joined science.xyz to work on fundamental problems in neural coding & build next-generation high-dimensional brain computer interfaces. The team is amazing and gives new meaning to the term "full-stack"
Science | Science Corporation
From science.xyz
34K
Sophia Sanborn
@naturecomputes
Aug 31, 2024
Seeking: Exceptional computer vision engineers with expertise in SOTA techniques Join Enigma as we push boundaries in neural decoding and neuroAI Interested? CV + brief cover letter to [email protected] enigmaproject.ai
22K
Sophia Sanborn
@naturecomputes
Aug 21, 2024
Seeking: Neuroscience Postdocs for Enigma @Stanford We're reimagining academic research. Join our interdisciplinary effort to decrypt the neural code: - Collaborative sci-eng team - Cutting-edge tools & tech - Dynamic, startup-like environment enigmaproject.ai
Katrin Franke
@kfrankelab
Aug 21, 2024
🚨We're hiring @StanfordMed @Stanford *Postdoc in visual & systems neuroscience* Focus on experiment design (visual stimuli, behavior etc)👇 Join our collaborative effort w/ @AToliasLab @naturecomputes @KonstantinWille @eywalker& more Please retweet t.ly/bVdk8
55K